Model Based Methods (MBD) vs. Data Driven Methods (DDM)

To analyze any dynamic system there could be two approaches; first is Model Based Methods (MBD) which requires knowledge of the physics of the system and second is Data Driven Methods (DDM) which is driven by the input, output and testdata to derive the system. Naturally, each method has its own advantages and disadvantages. MBD provides insight into the behavior of the system by using differenial equations, state space equations etc. On the negative side, MBD is time consuming and it cannot model system which contains nonlinear parameters or system is nonlinear. Contrary, DDM a fast and easy to develop methods which requires input output data to train the algorithms and learn the system parameters. DDM requires multiple data sets to cover a wide range of system operations.

Challenge lies on integrating MBD and DDM. MATLAB and Simulink offers a good platform to test both approaches. It will be valuable if MBD and DDM can be performed under one umbrella.